Map Building of Indoor Unknown Environment Based on Robot Service Mission Direction

Three-level indoor space maps including global semantic layer, region planning layer and local space layer are built for indoor mobile robot service mission. Using the space maps, the robot not only knows the plane structure of the environment for navigation, but also obtains three-dimensional grid map of local complicated space and semantic information which can describe the function, relationship and ascription of the room and the object. Firstly, depth information acquired by vision and object function information acquired by QR (quick response) code label are used to build a three-dimensional grid map and an object function map which describe local space. Then a planar grid map is built based on Bayesian estimation algorithm, simultaneously an undirected weighted map is formed, so the region planning layer is achieved. Lastly, roomdivision topology map is built based on clustering algorithms, and semantic information including functional information and relationship of rooms, object-room ascription is obtained, which constitute global semantic topology map. The simulation results show that three-level indoor space maps are applicable to indoor robot service tasks by understanding human semantic statement, producing reasonable service path, and ensuring robot running safely in complicated environment.